FAME, a 2.61M-parameter VGG-19 plus attention LSTM network, attributes face-swap deepfake videos to their generating models with reported accuracies of 79.7% on DFDM, 97.5% on FF++, and 96.8% on FakeAVCeleb.
Openface 2.0: Facial behavior analysis toolkit
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
FAME: A Lightweight Spatio-Temporal Network for Model Attribution of Face-Swap Deepfakes
FAME, a 2.61M-parameter VGG-19 plus attention LSTM network, attributes face-swap deepfake videos to their generating models with reported accuracies of 79.7% on DFDM, 97.5% on FF++, and 96.8% on FakeAVCeleb.